大模型对齐与安全

When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

Mahdi Dhaini, Stephen Meisenbacher, Ege Erdogan, Florian Matthes, Gjergji Kasneci

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.CL

Comments Accepted to AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025)

RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation System

Abdolazim Rezaei, Mehdi Sookhak, Mahboobeh Haghparast

机构 * Department of Computer Science Texas A\&M University Corpus Christi, USA（计算机科学系德克萨斯A&M大学科罗拉多州科罗拉多市） 纠错

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.AI

Using the NANDA Index Architecture in Practice: An Enterprise Perspective

Sichao Wang, Ramesh Raskar, Mahesh Lambe, Pradyumna Chari, Rekha Singhal, Shailja Gupta, Rajesh Ranjan, Ken Huang

机构 * Cisco Systems（思科系统） ； MIT（麻省理工学院） ； Unify Dynamics ； Tata Consultancy Services（塔塔咨询公司） ； CMU（卡内基梅隆大学） 纠错

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.AI

CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models

Shunchang Liu, Zhuan Shi, Lingjuan Lyu, Yaochu Jin, Boi Faltings

机构 * EPFL（苏黎世联邦理工学院） ； Mila - Quebec AI Institute Mcgill University（蒙特利尔麦吉尔大学人工智能研究所） ； Westlake University（西湖大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI

Comments Accepted by ACM MM 2025

Depth Gives a False Sense of Privacy: LLM Internal States Inversion

Tian Dong, Yan Meng, Shaofeng Li, Guoxing Chen, Zhen Liu, Haojin Zhu

机构 * Shanghai Jiao Tong University（上海交通大学） ； Southeast University（东南大学） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI

Comments Accepted by USENIX Security 2025. Please cite this paper as "Tian Dong, Yan Meng, Shaofeng Li, Guoxing Chen, Zhen Liu, Haojin Zhu. Depth Gives a False Sense of Privacy: LLM Internal States Inversion. In the 34th USENIX Security Symposium (USENIX Security '25)."

Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative Approaches

Xiaozheng Gao, Yichen Wang, Bosen Liu, Xiao Zhou, Ruichen Zhang, Jiacheng Wang, Dusit Niyato, Dong In Kim, Abbas Jamalipour, Chau Yuen, Jianping An, Kai Yang

机构 * School of Information and Electronics, Beijing Institute of Technology（信息与电子学院，北京理工大学） ； College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学） ； Department of Electrical and Computer Engineering, Sungkyunkwan University（电气与计算机工程系，首尔大学） ； School of Electrical and Computer Engineering, University of Sydney（电气与计算机工程学院，悉尼大学） ； School of Electrical and Electronics Engineering, Nanyang Technological University（电气与电子工程学院，南洋理工大学） ； School of Cyberspace Science and Technology, Beijing Institute of Technology（网络空间科学与技术学院，北京理工大学） 纠错

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.LG

Navigating the United States Legislative Landscape on Voice Privacy: Existing Laws, Proposed Bills, Protection for Children, and Synthetic Data for AI

Satwik Dutta, John H. L. Hansen

机构 * Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, USA（稳健语音系统中心（CRSS），德克萨斯大学达拉斯分校） 纠错

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.CY

Comments 5 pages, 2 figures, accepted at the Interspeech SynData4GenAI 2024 workshop

SoK: Semantic Privacy in Large Language Models

Baihe Ma, Yanna Jiang, Xu Wang, Guangsheng Yu, Qin Wang, Caijun Sun, Chen Li, Xuelei Qi, Ying He, Wei Ni, Ren Ping Liu

机构 * University of Technology Sydney, Australia（悉尼技术大学） ； Zhejiang Lab, China（浙江实验室） ； Northeastern University, China（东北大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI

Better Aligned with Survey Respondents or Training Data? Unveiling Political Leanings of LLMs on U.S. Supreme Court Cases

Shanshan Xu, T. Y. S. S Santosh, Yanai Elazar, Quirin Vogel, Barbara Plank, Matthias Grabmair

机构 * Technical University of Munich（慕尼黑技术大学） ； Allen Institute for AI（艾伦人工智能研究所） ； University of Washington（华盛顿大学） ； LMU Munich & Munich Center for Machine Learning (MCML)（慕尼黑大学及慕尼黑机器学习中心） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL

Query as Test: An Intelligent Driving Test and Data Storage Method for Integrated Cockpit-Vehicle-Road Scenarios

Shengyue Yao, Runqing Guo, Yangyang Qin, Miangbing Meng, Jipeng Cao, Yilun Lin, Yisheng Lv, Fei-Yue Wang

机构 * Peking University International Innovation Center, Lin-gang Special Area (PKU-IICSH)（北京大学国际创新中心，临港特殊区域（PKU-IICSH）） ； Onesyn (Shanghai) Technology Co., Ltd（上海奥森科技有限公司） ； CATARC Automotive Technology(Shanghai) Co.,Ltd（CATARC汽车技术（上海）有限公司） ； ZEEKR Intelligent Technology Holding Limited（ZEKR智能技术控股有限公司） ； Department of Automation, Tsinghua University（清华大学自动化系） ； State Key Laboratory for Management and Control of Complex Systems, Chinese Academy of Sciences（复杂系统管理与控制国家重点实验室，中国科学院） ； Macao Institute of Systems Engineering, Macau University of Science and Technology（澳门系统工程研究院，澳门科技大学） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI

Comments Submitted to IEEE Transaction on Vehicular Technology

Mechanistic Interpretability in the Presence of Architectural Obfuscation

Marcos Florencio, Thomas Barton

机构 * INTELI – Institute of Technology and Leadership（INTELI — 技术与领导力研究所） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI

Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges

Yanli Li, Zhongliang Guo, Nan Yang, Huaming Chen, Dong Yuan, Weiping Ding

机构 * School of Artificial Intelligence and Computer Science, Nantong University（人工智能与计算机科学学院，南通大学） ； School of Electrical and Computer Engineering, The University of Sydney（电气与计算机工程学院，悉尼大学） ； University of St Andrews（圣安德鲁大学） 纠错

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.AI

Journal ref IEEE Transactions on Neural Networks and Learning Systems, 2025, Page(s): 1 - 21

KGMark: A Diffusion Watermark for Knowledge Graphs

Hongrui Peng, Haolang Lu, Yuanlong Yu, Weiye Fu, Kun Wang, Guoshun Nan

机构 * Beijing University Of Posts and Telecommunications（北京邮电大学） ； Nanyang Technological University（南洋理工大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI

Comments Accepted by ICML2025

StreamLink: Large-Language-Model Driven Distributed Data Engineering System

Dawei Feng, Di Mei, Huiri Tan, Lei Ren, Xianying Lou, Zhangxi Tan

机构 * Tsinghua University（清华大学） ； King & Wood Mallesons（金杜律师事务所） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI

Comments Accepted by CIKM Workshop 2024, https://sites.google.com/view/cikm2024-rag/papers?authuser=0#h.ddm5fg2z885t

Ontology- and LLM-based Data Harmonization for Federated Learning in Healthcare

Natallia Kokash, Lei Wang, Thomas H. Gillespie, Adam Belloum, Paola Grosso, Sara Quinney, Lang Li, Bernard de Bono

机构 * Institute of Informatics University of Amsterdam（信息学院阿姆斯特丹大学） ； College of Medicine The Ohio State University（医学学院俄亥俄州立大学） ； Department of Neuroscience University of California（神经科学系加州大学） ； School of Medicine Indiana University（医学院印第安纳大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Comments Related dataset: https://doi.org/10.5281/zenodo.15411810

PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance

Haoran Li, Wenbin Hu, Huihao Jing, Yulin Chen, Qi Hu, Sirui Han, Tianshu Chu, Peizhao Hu, Yangqiu Song

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL

Comments Accepted by ACL 2025

An Efficient Private GPT Never Autoregressively Decodes

Zhengyi Li, Yue Guan, Kang Yang, Yu Feng, Ning Liu, Yu Yu, Jingwen Leng, Minyi Guo

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Comments Accepted by ICML 2025

Modular Federated Learning: A Meta-Framework Perspective

Frederico Vicente, Cláudia Soares, Dušan Jakovetić

机构 * NOVA School of Science and Technology（NOVA科学与技术学校） ； University of Novi Sad（诺维萨德大学） ； Faculty of Sciences（科学学院） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Synthesizing Diverse Network Flow Datasets with Scalable Dynamic Multigraph Generation

Arya Grayeli, Vipin Swarup, Steven E. Noel

机构 * The MITRE Corporation（MITRE公司） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Preserving Privacy and Utility in LLM-Based Product Recommendations

Tina Khezresmaeilzadeh, Jiang Zhang, Dimitrios Andreadis, Konstantinos Psounis

机构 * University of Southern California（南加州大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions

James D. Finch, Yasasvi Josyula, Jinho D. Choi

机构 * Department of Computer Science（计算机科学系） ； Emory University（埃默里大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL

Comments Accepted (B) to TACL 2025

Automating Pharmacovigilance Evidence Generation: Using Large Language Models to Produce Context-Aware SQL

Jeffery L. Painter, Venkateswara Rao Chalamalasetti, Raymond Kassekert, Andrew Bate

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI

Comments 15 pages, 3 tables, 5 figures

Privacy Meets Explainability: Managing Confidential Data and Transparency Policies in LLM-Empowered Science

Yashothara Shanmugarasa, Shidong Pan, Ming Ding, Dehai Zhao, Thierry Rakotoarivelo

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI

Comments 8 pages

Machine Learning for Synthetic Data Generation: A Review

Yingzhou Lu, Lulu Chen, Yuanyuan Zhang, Minjie Shen, Huazheng Wang, Xiao Wang, Capucine van Rechem, Tianfan Fu, Wenqi Wei

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising

Ashutosh Chaubey, Anoubhav Agarwaal, Sartaki Sinha Roy, Aayush Agrawal, Susmita Ghose

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI

Comments Published at WACV 2025

Bayesian Pseudo Posterior Mechanism for Differentially Private Machine Learning

Robert Chew, Matthew R. Williams, Elan A. Segarra, Alexander J. Preiss, Amanda Konet, Terrance D. Savitsky

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Federated Cross-Domain Click-Through Rate Prediction With Large Language Model Augmentation

Jiangcheng Qin, Xueyuan Zhang, Baisong Liu, Jiangbo Qian, Yangyang Wang

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL

FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors

Changlong Shi, He Zhao, Bingjie Zhang, Mingyuan Zhou, Dandan Guo, Yi Chang

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Comments Accepted in CVPR 2025

Secure On-Device Video OOD Detection Without Backpropagation

Shawn Li, Peilin Cai, Yuxiao Zhou, Zhiyu Ni, Renjie Liang, You Qin, Yi Nian, Zhengzhong Tu, Xiyang Hu, Yue Zhao

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI

Differentially Private Learners for Heterogeneous Treatment Effects

Maresa Schröder, Valentyn Melnychuk, Stefan Feuerriegel

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments Published at ICLR 2025